V1 (Anima Colab):60-image Lora capable of generating images in the style of Source Filmmaker renders featuring My Little Pony characters. Model created in Google Colab. Art styles from SFM artists included in the dataset:ddunsgodoffuryhooves-artindigosfmlunar57mr.tektitescrewingwithsfmsnuddyPrompts: 3d \(artwork\), source filmmaker \(artwork\), my little pony, friendship is magic,Negative prompts: low quality, worst quality, text, signature, watermarkBase model: anima-base-v1.0Resolution: 1024Repeats: 2Flip Augmentation: OffShuffle Tags: OnActivation Tags: 2Steps: 1200Epochs: 20Unet LR: 2e-5Text Encoder LR: 5e-5LR Scheduler: cosine_with_restartsLR Scheduler Number: 2LR Warmup Ratio: 0.1Min-SNR Gamma: 5IP Noise Gamma: 0.05Network Dim: 32Network Alpha: 16Train Batch Size: 2Optimizer: AdamW8BitV1 (NoobAI):50-image Lora capable of generating images in the style of Source Filmmaker renders featuring My Little Pony characters.Art styles from SFM artists included in the dataset:ddunsgodoffuryhooves-artindigosfmlunar57mr.tektitescrewingwithsfmsnuddyPrompts: 3d \(artwork\), source filmmaker \(artwork\), my little pony, friendship is magic,Negative prompts: low quality, worst quality, text, signature, watermarkBase model: NoobAI-XL EPS 1.1Repeats: 5Steps: 834Epochs: 20Unet LR: 0.0001Text Encoder LR: 0.00001LR Scheduler: constantLR Scheduler Cycles: 1Network Dim: 64Network Alpha: 32

MLP SFM Style - [NoobAI/Anima]

This was supposed to be a 20-epoch Lora, but it ended up being 18. That's because the power went out and interrupted the model training I was doing.

Files with SHA256: 4f08a5fd968878d60b9f7370b5ba70793520b51ed110107c2dbb782d88924096